{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.081744432449341, "min": 2.0488898754119873, "max": 2.1603426933288574, "count": 270 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41168.578125, "min": 31297.5, "max": 117165.6953125, "count": 270 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.85507246376811, "min": 23.046948356807512, "max": 84.19298245614036, "count": 270 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19556.0, "min": 17460.0, "max": 21616.0, "count": 270 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1734.9832224126098, "min": 1662.2893379839356, "max": 1735.931274737205, "count": 270 }, "SoccerTwos.Self-play.ELO.sum": { "value": 239427.68469294015, "min": 193027.5774977716, "max": 716958.7468452714, "count": 270 }, "SoccerTwos.Step.mean": { "value": 12699976.0, "min": 10009974.0, "max": 12699976.0, "count": 270 }, "SoccerTwos.Step.sum": { "value": 12699976.0, "min": 10009974.0, "max": 12699976.0, "count": 270 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.03555164858698845, "min": -0.10712188482284546, "max": 0.10014089196920395, "count": 270 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.906127452850342, "min": -26.60957145690918, "max": 16.861183166503906, "count": 270 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.03554387763142586, "min": -0.10463898628950119, "max": 0.1030474305152893, "count": 270 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.905055046081543, "min": -26.529645919799805, "max": 17.37087631225586, "count": 270 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 270 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 270 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.17189565084982608, "min": -0.38510000017973095, "max": 0.2787740458058947, "count": 270 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 23.721599817276, "min": -60.096800327301025, "max": 57.27400028705597, "count": 270 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.17189565084982608, "min": -0.38510000017973095, "max": 0.2787740458058947, "count": 270 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 23.721599817276, "min": -60.096800327301025, "max": 57.27400028705597, "count": 270 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 270 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 270 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01668496475322172, "min": 0.011030803911853581, "max": 0.024288988823536785, "count": 130 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01668496475322172, "min": 0.011030803911853581, "max": 0.024288988823536785, "count": 130 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08934229289491971, "min": 0.08279965842763583, "max": 0.12256046930948893, "count": 130 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08934229289491971, "min": 0.08279965842763583, "max": 0.12256046930948893, "count": 130 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08996559505661329, "min": 0.08339558045069377, "max": 0.1268399953842163, "count": 130 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08996559505661329, "min": 0.08339558045069377, "max": 0.1268399953842163, "count": 130 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0010000000000000002, "min": 0.0010000000000000002, "max": 0.0010000000000000002, "count": 130 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0010000000000000002, "min": 0.0010000000000000002, "max": 0.0010000000000000002, "count": 130 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 130 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 130 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 130 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 130 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676042421", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/home/olav/dev/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=deep-net6-cuda --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1676044378" }, "total": 1957.0452670440136, "count": 1, "self": 0.2587930599984247, "children": { "run_training.setup": { "total": 0.2751830799970776, "count": 1, "self": 0.2751830799970776 }, "TrainerController.start_learning": { "total": 1956.511290904018, "count": 1, "self": 0.590360515343491, "children": { "TrainerController._reset_env": { "total": 12.207031826925231, "count": 29, "self": 12.207031826925231 }, "TrainerController.advance": { "total": 1943.3630693057494, "count": 8113, "self": 0.20789785819943063, "children": { "env_step": { "total": 1169.1839708438492, "count": 8113, "self": 427.790684501495, "children": { "SubprocessEnvManager._take_step": { "total": 740.5530219544016, "count": 242063, "self": 18.53567612284678, "children": { "TorchPolicy.evaluate": { "total": 722.0173458315548, "count": 444119, "self": 722.0173458315548 } } }, "workers": { "total": 0.8402643879526295, "count": 8112, "self": 0.0, "children": { "worker_root": { "total": 62550.691039116355, "count": 241983, "is_parallel": true, "self": 60877.232960887544, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.10732071599340998, "count": 54, "is_parallel": true, "self": 0.043847165507031605, "children": { "_process_rank_one_or_two_observation": { "total": 0.06347355048637837, "count": 216, "is_parallel": true, "self": 0.06347355048637837 } } }, "UnityEnvironment.step": { "total": 0.4450260089652147, "count": 27, "is_parallel": true, "self": 0.013338808057596907, "children": { "UnityEnvironment._generate_step_input": { "total": 0.01023805994191207, "count": 27, "is_parallel": true, "self": 0.01023805994191207 }, "communicator.exchange": { "total": 0.3823790679452941, "count": 27, "is_parallel": true, "self": 0.3823790679452941 }, "steps_from_proto": { "total": 0.039070073020411655, "count": 54, "is_parallel": true, "self": 0.008043105102842674, "children": { "_process_rank_one_or_two_observation": { "total": 0.03102696791756898, "count": 216, "is_parallel": true, "self": 0.03102696791756898 } } } } } } }, "steps_from_proto": { "total": 2.203449579712469, "count": 1792, "is_parallel": true, "self": 0.4150967358145863, "children": { "_process_rank_one_or_two_observation": { "total": 1.7883528438978828, "count": 7168, "is_parallel": true, "self": 1.7883528438978828 } } }, "UnityEnvironment.step": { "total": 1671.2546286490979, "count": 241956, "is_parallel": true, "self": 105.7916552357492, "children": { "UnityEnvironment._generate_step_input": { "total": 71.35252055901219, "count": 241956, "is_parallel": true, "self": 71.35252055901219 }, "communicator.exchange": { "total": 1188.8552750422386, "count": 241956, "is_parallel": true, "self": 1188.8552750422386 }, "steps_from_proto": { "total": 305.2551778120978, "count": 483912, "is_parallel": true, "self": 60.01906124604284, "children": { "_process_rank_one_or_two_observation": { "total": 245.236116566055, "count": 1935648, "is_parallel": true, "self": 245.236116566055 } } } } } } } } } } }, "trainer_advance": { "total": 773.9712006037007, "count": 8112, "self": 14.745374999300111, "children": { "process_trajectory": { "total": 358.5414051635307, "count": 8112, "self": 358.08554103953065, "children": { "RLTrainer._checkpoint": { "total": 0.4558641240000725, "count": 5, "self": 0.4558641240000725 } } }, "_update_policy": { "total": 400.68442044086987, "count": 130, "self": 294.079748710501, "children": { "TorchPOCAOptimizer.update": { "total": 106.60467173036886, "count": 3900, "self": 106.60467173036886 } } } } } } }, "trainer_threads": { "total": 7.300113793462515e-07, "count": 1, "self": 7.300113793462515e-07 }, "TrainerController._save_models": { "total": 0.3508285259886179, "count": 1, "self": 0.0009537609876133502, "children": { "RLTrainer._checkpoint": { "total": 0.34987476500100456, "count": 1, "self": 0.34987476500100456 } } } } } } }